Stress In Rock Mass Research Articles

Modeling Brittle-to-Ductile Transitions in Rock Masses: Integrating the Geological Strength Index with the Hoek–Brown Criterion

Many studies focus on brittle–ductile transition stress in intact rocks; however, in real life, we deal with rock mass which contains many discontinuities. To fill this gap, this research focuses on the brittle–ductile transition stress of rock mass by considering the influence of different Geological Strength Index (GSI) values on the brittle–ductile transition stress of rock mass. In other words, the Hoek–Brown failure criteria for rock mass were reformulated mathematically including the ductility parameter (d), which is defined as the ratio of differential stress to minor stress. Then, the results were analyzed and plotted between σ3*σc and GSI, considering different (d) and Hoek–Brown material constant (mi) values. The brittle–ductile transition stress, σ3*, was determined by intersecting the Hoek–Brown failure envelope with Mogi’s line, with ductility parameters d ranging from 3.4 (silicate rocks) to 5.0 (carbonate rocks). Numerical solutions were derived for σ3*σc as a function of GSI using Matlab, and the results were fitted with an exponential model. The analysis revealed an exponential relationship between σ3*σc and GSI for values above 32, with accuracy better than 3%. Increased ductility reduces rock mass strength, with higher d values leading to lower σ3*σc. The diminishing returns in confinement strength at higher GSI values suggest that rock masses with higher GSI can sustain more confinement but with reduced effectiveness as GSI increases. These findings provide a framework for predicting brittle–ductile transitions in rock engineering.

Deformation and Stress of Rock Masses Surrounding a Tunnel Shaft Considering Seepage and Hard Brittleness Damage

Deformation and Stress of Rock Masses Surrounding a Tunnel Shaft Considering Seepage and Hard Brittleness Damage

Integrating the Finite Element Method with Python Scripting to Assess Mining Impacts on Surface Deformations

Mining operations disrupt the structure of rock layers, leading to surface deformations and potential mining damage. This issue has been extensively studied since the 19th century using various analytical, geometric-integral, and stochastic methods. Since the 1990s, numerical methods have been increasingly applied to determine changes in the stress and strain states of rock masses due to mining activities. These methods account for numerous additional factors influencing surface deformation, offering significant advantages over classical approaches. However, modelling rock masses presents challenges, particularly in calibrating the mechanical parameters of rock layers, an area extensively researched with numerous publications. In this study, we determined the mechanical parameter values of rock layers at the advancing mining front using a custom Python script and Finite Element Method (FEM) numerical models. We also introduced a modification to evaluate the error of the estimated parameter values. Numerical analyses were conducted for the Piast–Ziemowit mine region in Poland, utilizing mining, geological, and surveying data. Our results demonstrate that accurate calibration of mechanical parameters is crucial for reliable predictions of surface deformations. The proposed methodology enhances the precision of numerical models, providing a more robust framework for assessing the impact of mining activities on rock layers.

Dynamic propagation of tensile and shear fractures induced by impact load in rock based on the dual bilinear cohesive zone model

PurposeThe purpose of this study is to simulate the tensile and shear types of fractures using the mixed fracture criteria considering the energy evolution based on the dual bilinear cohesive zone model and investigate the dynamic propagation of tensile and shear fractures induced by an impact load in rock. The propagation of tension and shear at different scales induced by the impact load is also an important aspect of this study.Design/methodology/approachIn this study, based on the well-developed dual bilinear cohesive zone model and combined finite element-discrete element method, the dynamic propagation of tensile and shear fractures induced by the impact load in rock is investigated. Some key technologies, such as the governing partial differential equations, fracture criteria, numerical discretisation and detection and separation, are introduced to form the global algorithm and procedure. By comparing with the tensile and shear fractures induced by the impact load in rock disc in typical experiments, the effectiveness and reliability of the proposed method are well verified.FindingsThe dynamic propagation of tensile and shear fractures in the laboratory- and engineering-scale rock disc and rock strata are derived. The influence of mesh sensitivity, impact load velocities and load positions are investigated. The larger load velocities may induce larger fracture width and entire failure. When the impact load is applied near the left support constraint boundary, concentrated shear fractures appear around the loading region, as well as induced shear fracture band, which may induce local instability. The proposed method shows good applicability in studying the propagation of tensile and shear fractures under impact loads.Originality/valueThe proposed method can identify fracture propagation via the stress and energy evolution of rock masses under the impact load, which has potential to be extended into the investigation of the mixed fractures and disturbance of in-situ stresses during dynamic strata mining in deep energy development.

Numerical simulation of blasting behavior of rock mass with cavity under high in-situ stress

With the shift of coal seam mining to the deep, the in-situ stress of coal and rock mass increases gradually. High ground stress can limit the generation of rock cracks caused by blasting, and blasting usually shows different crushing states than low stress conditions. In order to study the blasting expansion rule of rock mass with cavity under high ground stress and the rock mass fracture state under different side stress coefficients. In this paper, the effective range of blasting and the stress distribution under blasting load are analyzed theoretically. The RHT (Riedel-Hiermaier-Thoma) model is used to numerically simulate the blasting process of rock mass with cavity under different ground stress, and the influence of ground stress and lateral pressure coefficient on the crack growth of rock mass is studied. The results show that when there is no ground stress, the damage cracks in rock mass are more concentrated in the horizontal direction and the fracture development tends to the direction where the holes are located, which confirms the guiding effect and stress concentration effect of the holes in rock mass, which helps to promote the crack penetration between the hole and the hole. The length difference of horizontal and vertical damage cracks in rock mass increases with the increase of horizontal and vertical stress difference. Under the same lateral stress coefficient, the larger the horizontal and vertical stress difference is, the stronger the inhibition effect on crack formation is. For blasting of rock mass with high ground stress, the crack formation length between gun holes decreases with the increase of stress level, and the crack extends preferentially in the direction of higher stress. Therefore, the placement of gun holes along the direction of greater stress and the shortening of hole spacing are conducive to the penetration of cracks between gun holes and empty holes. The research can provide reference for rock breaking behavior of deep rock mass blasting.

Experimental study on the effect of flexible joints of a deep-buried tunnel across an active fault under high in-situ stress conditions

During dislocation, a tunnel crossing the active fault will be damaged to varying degrees due to its permanent stratum displacement. Most previous studies did not consider the influence of the tunnel’s deep burial and the high in-situ stress, so the results were not entirely practical. In this paper, the necessity of solving the anti-dislocation problem of deep-buried tunnels is systemically discussed. Through the model test of tunnels across active faults, the differences in failures between deep-buried tunnels and shallow-buried tunnels were compared, and the dislocation test of deep-buried segmental tunnels was carried out to analyze the external stress change, lining strain, and failure mode of tunnels. The results are as follows: (1) The overall deformation of deep-buried and shallow-buried tunnels is both S-shaped. The failure mode of deep-buried tunnels is primarily characterized by shear and tensile failure, resulting in significant compressive deformation and a larger damaged area. In contrast, shallow-buried tunnels mainly experience shear failure, with the tunnel being sheared apart at the fault crossing, leading to more severe damage. (2) After the segmental structure design of the deep-buried tunnel, the “S” deformation pattern is transformed into a “ladder” pattern, and the strain of the tunnel and the peak stress of the external rock mass are reduced; therefore, damages are significantly mitigated. (3) Through the analysis of the distribution of cracks in the tunnel lining, it is found that the tunnel without a segmental structure design has suffered from penetrating failure and that cracks affect the entire lining. The cracks in a flexible segmental tunnel affect about 66.6% of the entire length of the tunnel, and cracks in a tunnel with a short segmental tunnel only affect about 33.3% of the entire length of the tunnel. Therefore, a deep-buried tunnel with a short segmental tunnel can yield a better anti-dislocation effect. (4) By comparing the shallow-buried segmental tunnel in previous studies, it is concluded that the shallow-buried segmental tunnel will also suffer from deformation outside the fault zone, while the damages to the deep-buried segmental tunnel are concentrated in the fault zone, so the anti-dislocation protection measures of the deep-buried tunnel shall be provided mainly in the fault zone. The results of the above study can provide theoretical reference and technical support for the design and reinforcement measures of the tunnel crossing active fault under high in-situ stress conditions.

Performance of double-arch tunnels under internal BLEVE

Double-arch tunnels, as one of the popular forms of tunnels, might be exposed to boiling liquid expanding vapour explosions (BLEVEs) associated with transported liquified petroleum gas (LPG), which could cause damage to the tunnel and even catastrophic collapse of the tunnel in extreme cases. However, very limited study has investigated the performance of double-arch tunnels when exposed to internal BLEVEs and in most analyses of tunnel responses to accidental explosions. The TNT-equivalence method was used to approximate the explosion load, which may lead to inaccurate tunnel response predictions. This study numerically investigates the response of typical double-arch tunnels to an internal BLEVE resulting from the instantaneous rupture of a 20 m3 LPG tank. Effects of various factors, including in-situ stresses, BLEVE locations, and lining configurations on tunnel responses are examined. The results show that the double-arch tunnels at their early-operation ages are more vulnerable to severe damage when exposed to the BLEVE due to the low action of in-situ stress of rock mass on the response of early-age tunnels. It is also found that directing the LPG tank to different driving lanes inside tunnels can affect the BLEVE-induced tunnel response more significantly than varying the configurations of tunnel lining. Moreover, installing section-steel arches in the mid-wall can effectively improve the blast resistance of the double-arch tunnels against the internal BLEVE. In addition, the prediction models based on multi-variate nonlinear regressions and machine learning methods are developed to predict the BLEVE-induced damage levels of the double-arch tunnels without and with section-steel arches.

Steel Arch and Rock Bolt Support in Terms of the Gateroad Stability Maintaining behind the Longwall Face

The longwall system is an extraction system commonly used in coal mining in many countries, including Poland. One of the methods for reducing extraction costs is the dual use of the gateroad. In the first instance, the gateroad serves as the tailgate, and during the exploitation of the second coal panel, it functions as the headgate. Such a situation requires maintenance of the roadway behind the longwall face, which is typically challenging, due to significant stress-related loads on the support and its substantial deformation. The support design for this kind of roadway should take into consideration the dual impact of exploitation pressure and the caved zone influence behind the longwall face. This article presents the results of in-situ research conducted on two roadways behind the longwall face. In both roadways, the effectiveness of specially designed steel arch frames and rock bolt patterns were examined to minimize roadway deformations and maintain their functionality. The research project was comprised of several stages. Initially, mining and laboratory studies were conducted to determine the geomechanical parameters of the rocks. Subsequently, excavation stability and functionality forecasts were performed based on the authors’ empirical indicators. Then, numerical analyses were carried out to design support schemes (steel arches and rock bolt) in both roadways. A fully automated monitoring system with programmed data loggers was designed to check the behaviour of a specific rock mass and the support elements. The load on the steel arch support was measured with the help of load cells, while the load on the rock bolt support was carried out with the help of measurement bolts. Behind the longwall face, the loads on the wooden cribs set from the goaf side were also monitored. Additionally, the measurement station was equipped with extensometers to monitor the movement of roof layers and stress meters to determine changes in rock mass stress. Laser scanning or traditional surveying methods were also used to verify the support schemes through roadway convergence measurements. The obtained results allowed us to draw conclusions regarding the optimization of support schemes and to give recommendations for the practical application of specific reinforcements in excavations maintained behind the longwall face.

Theoretical analysis of the interaction between blasting stress wave and linear interface crack under high in-situ stress in deep rock mass

This study theoretically investigates the scattering characteristics of blasting stress waves, treaded as elastic waves, at a linear interface crack in a deep rock mass with an even compressive in-situ stress field. First, the basic equations of the deep rock mass theoretically treaded as a homogeneous isotropic medium with an initial stress field are derived based on the linear elastic, finite deformation, plane strain, isotropic, and small deformation hypotheses, and incremental stress theory. The linear interface crack is theoretically treaded as two displacement-free boundaries, of which the interpolation displacements are described by introducing two dislocation density functions. Next, the mathematical model of the blasting stress wave scattering at the linear interface crack is established through a set of singular integral equations of the first type for these two dislocation density functions with Cauchy kernels. Finally, the dislocating and opening displacements of the linear interface crack and the displacement and effective stress fields of the scattered stress wave are numerically calculated. The principal stress field of the scattered stress wave is compared with the experimental data to qualitatively verify the rationality and correctness of the mathematical model. Theoretically, it is found that even compressive in-situ stress with an amplitude of tens of megapascals significantly affects the displacement and effective stress fields of the scattered stress wave near the linear interface crack. In conclusion, considering even compressive in-situ stress is greatly significant when studying the wave and scattering behaviors of deep rock masses. This mathematical model provides a theoretical guidance for the study of stress wave energy transformation and crack propagation in the process of rock blasting and mineral mining.

A new elasto-visco-plastic damage model and numerical simulation method used for time-dependent behavior prediction of deep tunnel

Accurately predicting the time-dependent behavior of surrounding rock is crucial for supporting design, revealing the mechanism of lining cracking and understanding long-term stability in deep-buried tunnels engineering. Based on the component combination model method and continuous damage mechanics theory, a New Elasto-Visco-Plastic Damage (NEVPD) model was proposed considering the characteristics of viscoelastic-plastic and the damage evolution of rocks. Three groups of experimental data were used for validating the model, and the results indicate that the model can effectively describe the time-dependent deformation characteristics of rocks at different stress levels. The dynamic link computer application program of the NEVPD model was procured through the secondary development interface of the FLAC3D software, and its validity was ascertained through test simulations. By investigating the influence of stress levels on creep parameters, a creep simulation approach considering the impact of rock mass stress state on the creep parameters was proposed for used in the long-term stability analysis of underground rock engineering. Finally, the time-dependent behavior of deep tunnel was predicted using two simulation approaches (the traditional method and the proposed method) based on the Burger-Creep Viscoplastic (CVISC) model built-in FLAC3D and the NEVPD model. The findings suggest that the proposed tunnel creep simulation approach provides a more precise reflection of the local deformation features of the surrounding rock compared to traditional methods. The simulation outcomes based on the NEVPD model exhibit the highest agreement with the field monitoring data.

Research on the variation law of floor stress information entropy in upper protective layer mining based on Brillouin optical fiber sensing

The characteristics of floor failure and stress changes during the mining process of protective layers are crucial for determining the effectiveness of pressure relief. Three boreholes were designed in the 21104 fully mechanized mining face of Hulusu Coal Mine to implant optical fibers into the floor of the working face. A fiber optic monitoring system was established to monitor the dynamic evolution of stress in the floor rock mass at different mining distances. Based on the information entropy in information theory, the monitoring results in the fiber optic monitoring system are calculated to obtain the stress information entropy at different mining distances. A quantitative dynamic analysis is conducted on the stress change process of the mining floor rock layer, and the stress change law of the protective layer after mining is verified through numerical calculation and similar simulation experiments. The results indicate that the evolution of stress information entropy can be divided into four stages, namely the original rock stress stage, stress concentration stage, stress release stage, and stress recovery stage. The stress information entropy shows a fluctuating upward trend, indicating that coal seam mining leads to a decrease in the orderliness of the overlying rock system and an increase in disorder. In different spatial evolution processes, there are also significant differences in stress information entropy. In the vertical direction, the entropy value of shallow rock layers changes greatly, while the entropy value of deep rock layers changes slightly. Mining leads to a decrease in the orderliness of the entire overlying rock system, an increase in stress information entropy, and a fluctuating upward trend in stress information entropy. The information entropy of overlying rock deformation and re compaction increases, but the degree of change of the former is greater than that of the latter. The Brillouin fiber optic sensing technology provides a new method for monitoring the stress changes in the protective layer mining floor, achieving quantitative analysis of floor rock failure.

Study on the formation mechanism of shale thermal cracks based on particle flow numerical simulation

Thermal effects on rock mass are involved in many fields, including enhanced oil and gas recovery, unconventional oil and gas development, and nuclear waste deep placement. Temperature change will produce thermal stress in rock mass, leading to thermal cracking. Thermal cracking of shale is frequently involved in these fields. The mechanism of thermal cracking formation in shale is studied in this paper using the method of indoor heating experiment and particle flow method, which discovered that it is difficult to produce obvious thermal cracking in shale matrix, and only a few intercrystalline and intercrystalline fractures and shrinkage fractures of organic matter occur locally. Based on the particle flow method, a shale particle flow model is built that is highly consistent with the macro and micro characteristics of shale, while the systematic calibration method for shale particle flow model microscopic parameters can realize effective calibration of shale particle flow mechanical model microscopic parameters. Using a linked thermodynamic coupling model of shale particle flow based on the mechanical model of shale particle flow, the impacts of heating modes, natural micro cracks, and confining pressures on the thermal cracking evolution of shale were studied.

Application of Neural Networks in Rock Mass Stress Assessment by Photoelasticity

Application of Neural Networks in Rock Mass Stress Assessment by Photoelasticity

Numerical manifold method for thermo-mechanical coupling simulation of fractured rock mass

As a calculation method based on the Galerkin variation, the numerical manifold method (NMM) adopts a double covering system, which can easily deal with discontinuous deformation problems and has a high calculation accuracy. Aiming at the thermo-mechanical (TM) coupling problem of fractured rock masses, this study uses the NMM to simulate the processes of crack initiation and propagation in a rock mass under the influence of temperature field, deduces related system equations, and proposes a penalty function method to deal with boundary conditions. Numerical examples are employed to confirm the effectiveness and high accuracy of this method. By the thermal stress analysis of a thick-walled cylinder (TWC), the simulation of cracking in the TWC under heating and cooling conditions, and the simulation of thermal cracking of the Swedish Äspö Pillar Stability Experiment (APSE) rock column, the thermal stress, and TM coupling are obtained. The numerical simulation results are in good agreement with the test data and other numerical results, thus verifying the effectiveness of the NMM in dealing with thermal stress and crack propagation problems of fractured rock masses.

The formation mechanism of dynamic water and mud inrush geohazard triggered by deep-buried tunnel crossing active fault: Insights from the geomechanical model test

Water and mud inrush geohazard is one of the most important geohazards for underground engineering. Understanding the formation mechanism of water and mud inrush is critical for directing the prevention and control of this geohazard. As a result, a large number of methods have provided insight into this topic, such as the geomechanical model test. However, this geohazard triggered by deep-buried tunnel crossing active fault has not yet been explored. Thus, this study develops a geomechanical model test system to simulate the dynamic water and mud inrush caused by Kangding No.2 tunnel crossing Yunongxi active fault. The results imply that seismic loading can result in fluctuating changes in seepage pressure and stress in the tunnel rock mass. Increasing seismic intensity broadens the fluctuation range, together with a dramatic rise in peak seepage pressure. The coupled effect of earthquake loading and high seepage pressure makes the water-resisting rock mass extremely vulnerable to fracturing, increasing the probability of water and mud inrush. High seismic intensity leads to rock fracture propagation, ulteriorly giving rise to stress releasing, eventually provoking the fracturing of rock mass. Precursor of water and mud inrush can be observed before the geohazard occurs, reflected by the gradual rise of seepage pressure and intermittent fluctuation of stress. Following the increasing earthquake intensity, peak acceleration occurs in a random position of water-resisting rock mass, but mostly appears at the tunnel contour of surrounding rock. The free face of the tunnel exerts an amplifying effect on seismic acceleration. Seismicity affects the formation of water and mud inrush from active fault, which ulteriorly determines the minimum safety thickness of water-resisting rock mass. Monitoring the seepage pressure and stress in water-resisting rock mass is effective for the early warning of inrush hazard.

Assessing a natural field of rock mass stress by means of in-situ measurements within Vostochnaya Sary-Oba deposit in Kazakhstan

Purpose is to assess a natural field of rock mass stress within Vostochnaya Sary-Oba deposit using in-situ measurements. It will help identify stress distribution as well as high-stress areas that may be dangerous for mining operations. Methods. The research has applied a technique of well hydraulic fracturing to study parameters of the initial stress field within the deposit. For the purpose, two metering points in two measuring (horizontal and vertical) wells were used. Hydraulic fracturing has been tested at each installation location. Findings. The in-situ measurement results have helped obtain quantitative parameters of stress-strain state of the rock mass. It has been understood that the available tectonic disturbances may result from the shape of structural folds as well as from tectonic fissility. Operating azimuth of the maximum horizontal stress within the points coincides, it is equal to 70° ± 10. Originality is the use of a new approach to assess the stress rock mass state within Vostochnaya Sary-Oba deposit while applying in-situ measurements and well hydraulic fracturing. The abovementioned favours more accurate and reliable assessment of rock stress state at the field being quite important for mining safety and for the development of the efficient supporting procedures and ore extraction procedures. Practical implications. The research results are applicable to adapt project documents for the deposit mining, a supporting technique selection, and ore extracting. Moreover, they will help make the substantiated choice of a structure and geotechnical parameters taking into consideration safety of operations as well as quality of ore mining. In addition, the results help develop measures to prevent rock mass outburst and fall in mine workings.

Stress redistribution in a multilayer chamber for compressed air energy storage in abandoned coalmine: Elastic analytical insights and material choice

AbstractCompressed air energy storage (CAES) is attracting attention as one of large‐scale renewable energy storage systems. Its gas storage chamber is one of key components for its success. A successful utilization of an abandoned coalmine roadway depends on the stability of the gas storage chamber. The chamber is a multilayer structure and the redistribution of the stress and displacement in each layer is critical to the chamber stability. So far, this redistribution mechanism under any lateral pressure coefficient and internal air pressure has been unclear and thus a quick and easy evaluation on the CAES chamber stability becomes difficult. In this study, the redistributions of stress and displacement in each layer are analytically solved based on complex variable function theory. First, the stress and displacement in three CAES multilayer structures are obtained under any lateral pressure coefficient and internal air pressure. Then, a comprehensive parameter b1 is obtained to describe the redistribution of stress and displacement in rock mass, lining layer, and grout layer. Its linkage with lateral pressure coefficient, internal air pressure, and material properties is analytically expressed. Thirdly, an analytical expression is obtained for the influence range of internal air pressure on chamber stress. Finally, the role and selection of lining and grouting layers are explored at different lateral pressure coefficient and internal air pressure. It is found that the CAES chamber stability can be effectively and quickly evaluated by these analytical solutions and comprehensive parameters and enhanced by a material with low bulk modulus but high shear modulus.

Fractal Study of the Development Law of Mining Cracks

Studying mining fracture development is vital for geotechnical and mining engineering and geological disaster prevention. This research assesses crack effects on rock mass stress equilibrium during coal mining, potentially causing geological disasters such as land subsidence and landslides. Using fractal geometry theory, the present study investigates the development of horizontal and vertical mining cracks, revealing their propagation patterns. The fractal dimension generally increases as the propulsion distance increases; however, fluctuations vary from 250 to 287.5 m, forming a wavering line chart. The proportion of mining fracture area relative to mining space area increases with greater propulsion distance, indicating expanded upward mining space due to separation layers. The horizontal distribution of mining cracks persists, while the vertical distribution decreases, suggesting ground subsidence results from upward transmission. The fastest increase in fractal dimension occurs at 87.5–100 m. At 250 m, it peaks at 1.4136, indicating complex crack structures. During propulsion, the fractal dimension decreases due to upward mining space expansion through overlying rock layer collapse, forming new cracks. The proportion of mining crack area to mining space area increases gradually throughout the mining process. The present study presents a simulation model for crack identification, noting limitations in identifying tiny cracks.

Research on Performance Test of the Optic-Electric Sensors for Reservoir Landslide Temperature Field Monitoring

In recent years, with the superposition of extreme climate, earthquakes, engineering disturbance and other effects, global landslide disasters occur frequently. Due to reservoir landslides being mostly in a multi-field coupling environment, the temperature field will impact the deformation and seepage fields, thereby affecting the stability of the reservoir landslide. The variation in the landslide’s surface temperature also directly affects the stress and deformation of deep rock masses. If hidden dangers are not detected in time, and corresponding measures are implemented, it is easy to cause landslide instability. In order to clarify the temperature measurement performance of different optic-electric sensors and the application characteristics of layout techniques, laboratory calibration tests of temperature sensors under different adhesives and attachment materials are carried out in this paper. It was found that the test data of the iron bar had the best effect among the four attachment materials overall. Therefore, the bar with a high-stiffness material should be preferred when selecting a pipe fitting as the fiber Bragg grating (FBG) temperature attachment in the borehole. However, considering the high requirements for the durability of sensors and layout techniques in on-site monitoring, the long-term stability of the adhesives used in actual monitoring needs to be improved. At the same time, it was found that the platinum 100 (PT100) temperature sensor has relatively higher testing accuracy (A: 0.15 + 0.002 × |t|; B: 0.30 + 0.005 × |t|), a larger temperature measurement range (−200~+850 °C) and better temperature measurement stability when compared to conventional sensors. Moreover, its resistance value has a good linear relationship with temperature. Finally, the Xinpu landslide in the Three Gorges Reservoir area was selected as the research object for on-site monitoring. There was a high correlation between the on-site monitoring results with the laboratory calibration test results. Therefore, through the performance test of optic-electric sensors in reservoir landslide temperature fields, more accurate solutions can be provided for selecting sensors and designing layout techniques to monitor the underground temperature field of landslides under different geological conditions. Thereby, grasping the real-time state information of the reservoir landslide temperature field is achieved accurately, providing an important reference for early warning, prediction, prevention and the control of reservoir landslide disasters.

Back analysis of rock mass parameters in tunnel engineering using machine learning techniques

Efficient determination of the rock mass properties is vitally important for calculating and evaluating tunnel stability in tunnel engineering. The back analysis method has been widely used as an indirect method for determining rock mass parameters based on field measurements. However, most back analysis methods are generally time-consuming for numerical simulation and are merely based on the measured displacement, which leads to the identification of rock mass parameters that cannot fully reflect the characteristics of the surrounding rock. To improve the accuracy of the estimation of rock mass parameters, this paper presents a back analysis method based on multi-output support vector regression (MSVR) and differential evolution (DE) algorithms. Firstly, the global sensitivity analysis of rock mass parameters is analyzed using the elementary effects method. Numerical simulation is then carried out to prepare training samples. DE algorithm is used to determine the optimum hyperparameters of MSVR. Based on the monitoring data, the rock mass properties of the selected sensitive parameters are estimated by the constructed MSVR model. A high-speed railway tunnel is utilized to demonstrate the effectiveness of the MSVR with the DE algorithm (DE-MSVR). The results show that the DE-MSVR with mixed monitoring data of vault settlement, convergence, and rock mass stress has higher forecasting performance than these models with a single type of monitoring data. It is feasible to use the monitoring data at the early stages combined with the numerical simulation for parameter back analysis. Moreover, the comparison results show that the presented method exhibits higher prediction accuracy than the existing back analysis models.